Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen3-VL

qwen.ai

Post reply on HN
Print view View original

161–166 of 166 posts

Re: Qwen3-VL

#161

Post by mhast »

Keyframe wrote: post #113
ricardobeat wrote: post #109

Earlier quoted context omitted.

Yes, but the mac costs 3-4x more. You can get one of these 395 systems with 96GB for ~1k.

When I was looking it was more like 1.6k euros, but still great price. Mac studio with M4 Max 16/40/16 with 128GB is double that. That's all within a range of "affordable". Now, if it's at least twice the speed, I don't see a reason not to. Even though my religion is against buying a mac as well. edit, just took a look at amazon. GMKtec EVO-X2 AI, which is the AMD Ryzen AI Max+ 395 with 128GB of RAM is 3k euros. Mac…

I have a M4 Max with 128 GB memory. Even on that machine I would not consider 70B+ models to be useable. Once you go below 20 tokens/s it becomes more like having a pen pal than an AI assistant.

MoE models can still be pretty fast. As are smaller models.

(This is mostly a warning for anyone who is enamored by the idea of running these things locally to make sure to test it before you spend a lot of money.)

Currently I'd probably say the Nvidia RTX pro 6000 is a Challenger if you want local models. It "only" has 96 GB of RAM, but it's very fast (1800 GB/s). If you can fit the model on it and it's good enough for your use case then it's probably worth it even at $10k.

Re: Qwen3-VL

#162

Post by rkomorn »

mhast wrote: post #161
Keyframe wrote: post #113

Earlier quoted context omitted.

When I was looking it was more like 1.6k euros, but still great price. Mac studio with M4 Max 16/40/16 with 128GB is double that. That's all within a range of "affordable". Now, if it's at least twice the speed, I don't see a reason not to. Even though my religion is against buying a mac as well. edit, just took a look at amazon. GMKtec EVO-X2 AI, which is the AMD Ryzen AI Max+ 395 with 128GB of RAM is 3k euros. Mac…

I have a M4 Max with 128 GB memory. Even on that machine I would not consider 70B+ models to be useable. Once you go below 20 tokens/s it becomes more like having a pen pal than an AI assistant. MoE models can still be pretty fast. As are smaller models. (This is mostly a warning for anyone who is enamored by the idea of running these things locally to make sure to test it before you spend a lot of money.) Currently…

> it becomes more like having a pen pal than an AI assistant

This is greatly phrased. Love it.

Re: Qwen3-VL

#163

Post by iamleppert »

iamflimflam1 wrote: post #92
richardlblair wrote: post #23

As I mentioned yesterday - I recently needed to process hundreds of low quality images of invoices (for a construction project). I had a script that had used pil/opencv, pytesseract, and open ai as a fallback. It still has a staggering number of failures. Today I tried a handful of the really poor quality invoices and Qwen spat out all the information I needed without an issue. What's crazier is it gave me the boundi…

I would recommend taking a look at this service: https://learn.microsoft.com/en-us/rest/api/computervision/re...

Microsoft Vision is so expensive and has a ridiculous rate limit, is slow, and isn't any better than what you can run yourself. You have to make every request over HTTP (with a rate limit), and there is no ability to do bulk jobs. It's also incredibly expensive.

Re: Qwen3-VL

#164

Post by lofaszvanitt »

richardlblair wrote: post #23

As I mentioned yesterday - I recently needed to process hundreds of low quality images of invoices (for a construction project). I had a script that had used pil/opencv, pytesseract, and open ai as a fallback. It still has a staggering number of failures. Today I tried a handful of the really poor quality invoices and Qwen spat out all the information I needed without an issue. What's crazier is it gave me the boundi…

People actually use tesseract? It's one of the worst OCR solutions out there. Forget it.

Re: Qwen3-VL

#165

Post by marci »

jychang wrote: post #158
marci wrote: post #152

Earlier quoted context omitted.

it's sometimes not really a matter of which one is better but which one fits best. For example many have switched to qwen3 models but some still vastly prefer the reasoning and output of QwQ (a qwen2.5 model). And the difference between them: those with "plus" are closed weight, you can only access them through their api. The others are open-weight, so if they fit your use case, and if ever the want or need arise, yo…

If the naming is so clear to you, then why don't you explain: for a user who wants to use Qwen3-VL through an API, which one has better performance? Qwen3-VL Plus or Qwen3-VL 235b?

My precedent post should have answered this question. But since it didn't, I think I'm ill equipped to answer you in a satisfactory fashion, I would just be repeating myself.

Re: Qwen3-VL

#166

Post by jychang »

marci wrote: post #165
jychang wrote: post #158

Earlier quoted context omitted.

If the naming is so clear to you, then why don't you explain: for a user who wants to use Qwen3-VL through an API, which one has better performance? Qwen3-VL Plus or Qwen3-VL 235b?

My precedent post should have answered this question. But since it didn't, I think I'm ill equipped to answer you in a satisfactory fashion, I would just be repeating myself.

Exactly. You're ill equipped to answer the question because you don't know. Qwen is terrible at explaining what the difference is, between the models that they serve on their API.

It's such a simple question: "For someone who does not want to run the model locally, what is the difference between these 2 models on the API?" and yet nobody can answer that question.

Post reply on HN